INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pun

-0.80

CVE

-0.79

tein

-0.78

apters

-0.77

ð

-0.75

rawdownloadcloneembedreportprint

-0.73

atech

-0.71

laughs

-0.66

loading

-0.66

jriwal

-0.65

POSITIVE LOGITS

sonian

0.84

Dod

0.71

«ĺ

0.70

ignty

0.66

 retri

0.63

DF

0.61

 Pamela

0.59

 Winn

0.59

 yielded

0.58

rane

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.